Vocapia is a provider of speech-to-text software and services, a flagship of them being the VoxSigma software suite. It caters to several applications including broadcast monitoring, seminar transcription, video subtitling, conference call transcription, and speech analytics. Leveraging advanced AI and machine learning methods, the platform allows large vocabulary continuous speech recognition, automatic audio segmentation, language identification, speaker diarization, and audio-text synchronization. The VoxSigma suite is widely applicable to multiple language types and diverse audio data types, including broadcast data, parliamentary hearings, and conversational data. It is designed for professional users seeking to transcribe considerable volumes of audio and video documents, either in batch mode or real-time, with specific versions created for transcribing conversational telephone speech and call-center data. The suite also provides transcription, audio indexing, and speech-text alignment capabilities via a REST API as a web service with the VoxSigma SaaS. This technology enables content-based information access in audio and video documents resulting in optimized downstream processing and direct access to relevant portions of audio documents. Additionally, the software supports language identification from a set of 82 languages, audiovisual data mining, speech analytics, and media asset management.
